PSI - Issue 64

First page Table of contents Previous page 2224 Next page Last page

ScienceDirect Structural Integrity Procedia 00 (2023) 000 – 000 Structural Integrity Procedia 00 (2023) 000 – 000 Available online at www.sciencedirect.com Available online at www.sciencedirect.com ScienceDirect Available online at www.sciencedirect.com ScienceDirect

www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia

Procedia Structural Integrity 64 (2024) 774–783

SMAR 2024 – 7th International Conference on Smart Monitoring, Assessment and Rehabilitation of Civil Structures Virtual Sensing in Steel Bridges: Time Series Deep Learning for Stress Prediction Bowen Meng a, *, Menghini Alessandro b , Leander John a a KTH Royal Institute of Technology, Brinellvägen 23, Stockholm 10044, Sweden b Politecnico di Milano, Via Giuseppe Ponzio 31, Milano 20133, Italy Abstract This study introduces an innovative approach for predicting stress responses in steel bridges, specifically focusing on a railway bridge in Vänersborg, Sweden. Four deep learning models have been evaluated: Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and a hybrid LSTM-TCN. Training on stress history data from a multiscale Finite Element (FE) model and a validation with real-world data from a bridge monitoring system revealed high prediction accuracy near sensor locations, surpassing an R-squared score of 0.9, comparable to the polynomial local response function method. The comparative analysis provides critical insights into the great potential of deep learning-based sequence models for identifying intricate, temporally dependent stress patterns across the bridge, including predictions at points distant from direct sensor measurements. These models demonstrate a notable capability for capturing highly non-linear relationships between stress histories. While sequence models (LSTM, TCN, and hybrid LSTM-TCN) tended to provide conservative estimates impacting fatigue life predictions, the MLP model occasionally underestimated critical stress cycles. This research emphasizes the potential of deep learning techniques for time series to enhance bridge monitoring systems, improve virtual sensing, and enable real-time monitoring capabilities. Our proposed methodology provides a comprehensive understanding of stress data in steel bridges, which is crucial for ensuring their maintenance and safety. © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers Keywords: Fatigue Life Prediction; Virtual Sensing; Time Series Modeling; Deep Learning SMAR 2024 – 7th International Conference on Smart Monitoring, Assessment and Rehabilitation of Civil Structures Virtual Sensing in Steel Bridges: Time Series Deep Learning for Stress Prediction Bowen Meng a, *, Menghini Alessandro b , Leander John a a KTH Royal Institute of Technology, Brinellvägen 23, Stockholm 10044, Sweden b Politecnico di Milano, Via Giuseppe Ponzio 31, Milano 20133, Italy Abstract This study introduces an innovative approach for predicting stress responses in steel bridges, specifically focusing on a railway bridge in Vänersborg, Sweden. Four deep learning models have been evaluated: Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and a hybrid LSTM-TCN. Training on stress history data from a multiscale Finite Element (FE) model and a validation with real-world data from a bridge monitoring system revealed high prediction accuracy near sensor locations, surpassing an R-squared score of 0.9, comparable to the polynomial local response function method. The comparative analysis provides critical insights into the great potential of deep learning-based sequence models for identifying intricate, temporally dependent stress patterns across the bridge, including predictions at points distant from direct sensor measurements. These models demonstrate a notable capability for capturing highly non-linear relationships between stress histories. While sequence models (LSTM, TCN, and hybrid LSTM-TCN) tended to provide conservative estimates impacting fatigue life predictions, the MLP model occasionally underestimated critical stress cycles. This research emphasizes the potential of deep learning techniques for time series to enhance bridge monitoring systems, improve virtual sensing, and enable real-time monitoring capabilities. Our proposed methodology provides a comprehensive understanding of stress data in steel bridges, which is crucial for ensuring their maintenance and safety. © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers Keywords: Fatigue Life Prediction; Virtual Sensing; Time Series Modeling; Deep Learning © 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers

* Bowen Meng. E-mail address: bowenm@kth.se * Bowen Meng. E-mail address: bowenm@kth.se

2452-3216 © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers 2452-3216 © 2024 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of SMAR 2024 Organizers

Made with FlippingBook Digital Proposal Maker